# SlashML (/ ml) Embodied Robotics Trajectory Memory

SlashML (/ ml) Embodied Robotics Trajectory Memory is an MCP server for Claude Code that exposes 6-DoF entity tracking, movement histories, and equipment affordances to physical reasoning agents.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1 repo stars
- Author: slashml-ai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/slashml-ai/slashml-robotics
- Updated: 2026-11-09
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/slashml-ml-embodied-robotics-trajectory-memory

## What it does

The server acts as an MCP gateway to SlashML Robotics, handling dynamic belief updates without coordinate obsolescence. Fresh sensor reports replace outdated coordinates in under 1 microsecond without triggered reindexing passes.

Agents receive access to dedicated tools: `locate_physical_object` for checking the active zone and 6-DoF pose, `record_sensor_observation` for ingesting perception detections, `query_object_trajectory` for waypoint inspection, and `find_objects_by_affordance` for tool lookups.

It connects across platforms via the hosted HTTP endpoint at `https://api.slashml.ai/robotics/mcp` or runs against local `slashmld` background instances tied to ROS 2 through `SlashMLSpatialBridgeNode`.

## Requirements
- Remote server: `https://api.slashml.ai/robotics/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http slashml-robotics https://api.slashml.ai/robotics/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add slashml-ml-embodied-robotics-trajectory-memory --url https://api.slashml.ai/robotics/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "slashml-ml-embodied-robotics-trajectory-memory": {
            "url": "https://api.slashml.ai/robotics/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "slashml-ml-embodied-robotics-trajectory-memory": {
            "type": "http",
            "url": "https://api.slashml.ai/robotics/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http slashml-ml-embodied-robotics-trajectory-memory https://api.slashml.ai/robotics/mcp
```

## When to use it
- Look up active 6-DoF coordinates and work zones for specific tools
- Retrieve timestamped waypoint histories for tracked objects
- Search workspace equipment by functional capability rather than class label
- Feed live camera detections into the memory substrate with low overhead

## Example prompts
- Check the active 6-DoF coordinates for digital_caliper
- Find workspace tools capable of cutting using find_objects_by_affordance
- Retrieve the waypoint trajectory history for wire_strippers

## Similar
- [robotics-subject-expert](https://affpapa.org/en/nevibecode/skills/robotics-subject-expert.md) — skill · 1 install
- [robotics-engineer](https://affpapa.org/en/nevibecode/agents/robotics-engineer.md) — subagent · ★ 2858 repo stars
- [ros2-robotics](https://affpapa.org/en/nevibecode/skills/ros2-robotics.md) — skill · 293 installs
- [srv-d7aoqmh5pdvs7391dcqg](https://affpapa.org/en/nevibecode/mcp/srv-d7aoqmh5pdvs7391dcqg.md) — MCP server · 4056 installs
- [mcp_server_ros_2](https://affpapa.org/en/nevibecode/mcp/mcp-server-ros-2.md) — MCP server · ★ 99 repo stars
- [sensor-fusion](https://affpapa.org/en/nevibecode/skills/sensor-fusion.md) — skill · 1 install

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
